fix (02-use-cases): AWS Operations Agent updated with AgentCore Runtime (#177)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
---------
Co-authored-by: name <alias@amazon.com>
2025-07-31 11:59:30 -07:00
|
|
|
|
#!/bin/bash
|
|
|
|
|
|
|
|
|
|
# Delete all AgentCore Runtimes
|
|
|
|
|
echo "🗑️ Deleting all AgentCore Runtimes..."
|
|
|
|
|
|
|
|
|
|
# Configuration - Get project directory
|
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
|
|
|
PROJECT_DIR="$(dirname "$(dirname "$SCRIPT_DIR")")" # Go up two levels to reach AgentCore root
|
|
|
|
|
RUNTIME_DIR="$(dirname "$SCRIPT_DIR")" # agentcore-runtime directory
|
|
|
|
|
CONFIG_DIR="${PROJECT_DIR}/config"
|
|
|
|
|
|
|
|
|
|
# Load configuration from YAML (fallback if yq not available)
|
|
|
|
|
if command -v yq >/dev/null 2>&1; then
|
Configuration Management Fixes (#223)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
* feat: Enhance AWS Operations Agent with improved testing and deployment
- Update README with new local container testing approach using run-*-local-container.sh scripts
- Replace deprecated SAM-based MCP Lambda deployment with ZIP-based deployment
- Add no-cache flag to Docker builds to ensure clean builds
- Update deployment scripts to use consolidated configuration files
- Add comprehensive cleanup scripts for all deployment components
- Improve error handling and credential validation in deployment scripts
- Add new MCP tool deployment using ZIP packaging instead of Docker containers
- Update configuration management to use dynamic-config.yaml structure
- Add local testing capabilities with containerized agents
- Remove outdated test scripts and replace with interactive chat client approach
* fix: Update IAM policy configurations
- Update bac-permissions-policy.json with enhanced permissions
- Update bac-trust-policy.json for improved trust relationships
* fix: Update Docker configurations for agent runtimes
- Update Dockerfile.diy with improved container configuration
- Update Dockerfile.sdk with enhanced build settings
* fix: Update OAuth iframe flow configuration
- Update iframe-oauth-flow.html with improved OAuth handling
* feat: Update AWS Operations Agent configuration and cleanup
- Update IAM permissions policy with enhanced access controls
- Update IAM trust policy with improved security conditions
- Enhance OAuth iframe flow with better UX and error handling
- Improve chatbot client with enhanced local testing capabilities
- Remove cache files and duplicate code for cleaner repository
* docs: Add architecture diagrams and update README
- Add architecture-2.jpg and flow.jpg diagrams for better visualization
- Update README.md with enhanced documentation and diagrams
* Save current work before resolving merge conflicts
* Keep AWS-operations-agent changes (local version takes precedence)
* Fix: Remove merge conflict markers from AWS-operations-agent files - restore clean version
* Fix deployment and cleanup script issues
Major improvements and fixes:
Configuration Management:
- Fix role assignment in gateway creation (use bac-execution-role instead of Lambda role)
- Add missing role_arn cleanup in MCP tool deletion script
- Fix OAuth provider deletion script configuration clearing
- Improve memory deletion script to preserve quote consistency
- Add Lambda invoke permissions to bac-permissions-policy.json
Script Improvements:
- Reorganize deletion scripts: 11-delete-oauth-provider.sh, 12-delete-memory.sh, 13-cleanup-everything.sh
- Fix interactive prompt handling in cleanup scripts (echo -e format)
- Add yq support with sed fallbacks for better YAML manipulation
- Remove obsolete 04-deploy-mcp-tool-lambda-zip.sh script
Architecture Fixes:
- Correct gateway role assignment to use runtime.role_arn (bac-execution-role)
- Ensure proper role separation between gateway and Lambda execution
- Fix configuration cleanup to clear all dynamic config fields consistently
Documentation:
- Update README with clear configuration instructions
- Maintain security best practices with placeholder values
- Add comprehensive deployment and cleanup guidance
These changes address systematic issues with cleanup scripts, role assignments,
and configuration management while maintaining security best practices.
* Update README.md with comprehensive documentation
Enhanced documentation includes:
- Complete project structure with 75 files
- Step-by-step deployment guide with all 13 scripts
- Clear configuration instructions with security best practices
- Dual agent architecture documentation (DIY + SDK)
- Authentication flow and security implementation details
- Troubleshooting guide and operational procedures
- Local testing and container development guidance
- Tool integration and MCP protocol documentation
The README now provides complete guidance for deploying and operating
the AWS Support Agent with Amazon Bedrock AgentCore system.
---------
Co-authored-by: name <alias@amazon.com>
2025-08-09 13:51:24 -07:00
|
|
|
|
REGION=$(yq eval '.aws.region' "${CONFIG_DIR}/static-config.yaml")
|
|
|
|
|
ACCOUNT_ID=$(yq eval '.aws.account_id' "${CONFIG_DIR}/static-config.yaml")
|
fix (02-use-cases): AWS Operations Agent updated with AgentCore Runtime (#177)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
---------
Co-authored-by: name <alias@amazon.com>
2025-07-31 11:59:30 -07:00
|
|
|
|
else
|
|
|
|
|
echo "⚠️ yq not found, using default values from existing config"
|
|
|
|
|
# Fallback: extract from YAML using grep/sed
|
Configuration Management Fixes (#223)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
* feat: Enhance AWS Operations Agent with improved testing and deployment
- Update README with new local container testing approach using run-*-local-container.sh scripts
- Replace deprecated SAM-based MCP Lambda deployment with ZIP-based deployment
- Add no-cache flag to Docker builds to ensure clean builds
- Update deployment scripts to use consolidated configuration files
- Add comprehensive cleanup scripts for all deployment components
- Improve error handling and credential validation in deployment scripts
- Add new MCP tool deployment using ZIP packaging instead of Docker containers
- Update configuration management to use dynamic-config.yaml structure
- Add local testing capabilities with containerized agents
- Remove outdated test scripts and replace with interactive chat client approach
* fix: Update IAM policy configurations
- Update bac-permissions-policy.json with enhanced permissions
- Update bac-trust-policy.json for improved trust relationships
* fix: Update Docker configurations for agent runtimes
- Update Dockerfile.diy with improved container configuration
- Update Dockerfile.sdk with enhanced build settings
* fix: Update OAuth iframe flow configuration
- Update iframe-oauth-flow.html with improved OAuth handling
* feat: Update AWS Operations Agent configuration and cleanup
- Update IAM permissions policy with enhanced access controls
- Update IAM trust policy with improved security conditions
- Enhance OAuth iframe flow with better UX and error handling
- Improve chatbot client with enhanced local testing capabilities
- Remove cache files and duplicate code for cleaner repository
* docs: Add architecture diagrams and update README
- Add architecture-2.jpg and flow.jpg diagrams for better visualization
- Update README.md with enhanced documentation and diagrams
* Save current work before resolving merge conflicts
* Keep AWS-operations-agent changes (local version takes precedence)
* Fix: Remove merge conflict markers from AWS-operations-agent files - restore clean version
* Fix deployment and cleanup script issues
Major improvements and fixes:
Configuration Management:
- Fix role assignment in gateway creation (use bac-execution-role instead of Lambda role)
- Add missing role_arn cleanup in MCP tool deletion script
- Fix OAuth provider deletion script configuration clearing
- Improve memory deletion script to preserve quote consistency
- Add Lambda invoke permissions to bac-permissions-policy.json
Script Improvements:
- Reorganize deletion scripts: 11-delete-oauth-provider.sh, 12-delete-memory.sh, 13-cleanup-everything.sh
- Fix interactive prompt handling in cleanup scripts (echo -e format)
- Add yq support with sed fallbacks for better YAML manipulation
- Remove obsolete 04-deploy-mcp-tool-lambda-zip.sh script
Architecture Fixes:
- Correct gateway role assignment to use runtime.role_arn (bac-execution-role)
- Ensure proper role separation between gateway and Lambda execution
- Fix configuration cleanup to clear all dynamic config fields consistently
Documentation:
- Update README with clear configuration instructions
- Maintain security best practices with placeholder values
- Add comprehensive deployment and cleanup guidance
These changes address systematic issues with cleanup scripts, role assignments,
and configuration management while maintaining security best practices.
* Update README.md with comprehensive documentation
Enhanced documentation includes:
- Complete project structure with 75 files
- Step-by-step deployment guide with all 13 scripts
- Clear configuration instructions with security best practices
- Dual agent architecture documentation (DIY + SDK)
- Authentication flow and security implementation details
- Troubleshooting guide and operational procedures
- Local testing and container development guidance
- Tool integration and MCP protocol documentation
The README now provides complete guidance for deploying and operating
the AWS Support Agent with Amazon Bedrock AgentCore system.
---------
Co-authored-by: name <alias@amazon.com>
2025-08-09 13:51:24 -07:00
|
|
|
|
REGION=$(grep "region:" "${CONFIG_DIR}/static-config.yaml" | head -1 | sed 's/.*region: *["'\'']*\([^"'\'']*\)["'\'']*$/\1/')
|
|
|
|
|
ACCOUNT_ID=$(grep "account_id:" "${CONFIG_DIR}/static-config.yaml" | head -1 | sed 's/.*account_id: *["'\'']*\([^"'\'']*\)["'\'']*$/\1/')
|
fix (02-use-cases): AWS Operations Agent updated with AgentCore Runtime (#177)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
---------
Co-authored-by: name <alias@amazon.com>
2025-07-31 11:59:30 -07:00
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
echo "📝 Configuration:"
|
|
|
|
|
echo " Region: $REGION"
|
|
|
|
|
echo " Account ID: $ACCOUNT_ID"
|
|
|
|
|
echo ""
|
|
|
|
|
|
|
|
|
|
# Get AWS credentials
|
|
|
|
|
echo "🔐 Getting AWS credentials..."
|
|
|
|
|
if [ -n "$AWS_PROFILE" ]; then
|
|
|
|
|
echo " Using AWS profile: $AWS_PROFILE"
|
|
|
|
|
aws configure list --profile "$AWS_PROFILE"
|
|
|
|
|
else
|
|
|
|
|
echo " Using default AWS credentials"
|
|
|
|
|
aws configure list
|
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
# Check AWS credentials
|
Configuration Management Fixes (#223)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
* feat: Enhance AWS Operations Agent with improved testing and deployment
- Update README with new local container testing approach using run-*-local-container.sh scripts
- Replace deprecated SAM-based MCP Lambda deployment with ZIP-based deployment
- Add no-cache flag to Docker builds to ensure clean builds
- Update deployment scripts to use consolidated configuration files
- Add comprehensive cleanup scripts for all deployment components
- Improve error handling and credential validation in deployment scripts
- Add new MCP tool deployment using ZIP packaging instead of Docker containers
- Update configuration management to use dynamic-config.yaml structure
- Add local testing capabilities with containerized agents
- Remove outdated test scripts and replace with interactive chat client approach
* fix: Update IAM policy configurations
- Update bac-permissions-policy.json with enhanced permissions
- Update bac-trust-policy.json for improved trust relationships
* fix: Update Docker configurations for agent runtimes
- Update Dockerfile.diy with improved container configuration
- Update Dockerfile.sdk with enhanced build settings
* fix: Update OAuth iframe flow configuration
- Update iframe-oauth-flow.html with improved OAuth handling
* feat: Update AWS Operations Agent configuration and cleanup
- Update IAM permissions policy with enhanced access controls
- Update IAM trust policy with improved security conditions
- Enhance OAuth iframe flow with better UX and error handling
- Improve chatbot client with enhanced local testing capabilities
- Remove cache files and duplicate code for cleaner repository
* docs: Add architecture diagrams and update README
- Add architecture-2.jpg and flow.jpg diagrams for better visualization
- Update README.md with enhanced documentation and diagrams
* Save current work before resolving merge conflicts
* Keep AWS-operations-agent changes (local version takes precedence)
* Fix: Remove merge conflict markers from AWS-operations-agent files - restore clean version
* Fix deployment and cleanup script issues
Major improvements and fixes:
Configuration Management:
- Fix role assignment in gateway creation (use bac-execution-role instead of Lambda role)
- Add missing role_arn cleanup in MCP tool deletion script
- Fix OAuth provider deletion script configuration clearing
- Improve memory deletion script to preserve quote consistency
- Add Lambda invoke permissions to bac-permissions-policy.json
Script Improvements:
- Reorganize deletion scripts: 11-delete-oauth-provider.sh, 12-delete-memory.sh, 13-cleanup-everything.sh
- Fix interactive prompt handling in cleanup scripts (echo -e format)
- Add yq support with sed fallbacks for better YAML manipulation
- Remove obsolete 04-deploy-mcp-tool-lambda-zip.sh script
Architecture Fixes:
- Correct gateway role assignment to use runtime.role_arn (bac-execution-role)
- Ensure proper role separation between gateway and Lambda execution
- Fix configuration cleanup to clear all dynamic config fields consistently
Documentation:
- Update README with clear configuration instructions
- Maintain security best practices with placeholder values
- Add comprehensive deployment and cleanup guidance
These changes address systematic issues with cleanup scripts, role assignments,
and configuration management while maintaining security best practices.
* Update README.md with comprehensive documentation
Enhanced documentation includes:
- Complete project structure with 75 files
- Step-by-step deployment guide with all 13 scripts
- Clear configuration instructions with security best practices
- Dual agent architecture documentation (DIY + SDK)
- Authentication flow and security implementation details
- Troubleshooting guide and operational procedures
- Local testing and container development guidance
- Tool integration and MCP protocol documentation
The README now provides complete guidance for deploying and operating
the AWS Support Agent with Amazon Bedrock AgentCore system.
---------
Co-authored-by: name <alias@amazon.com>
2025-08-09 13:51:24 -07:00
|
|
|
|
echo "🔍 Verifying AWS credentials..."
|
|
|
|
|
if aws sts get-caller-identity --region "$REGION" >/dev/null 2>&1; then
|
|
|
|
|
CALLER_IDENTITY=$(aws sts get-caller-identity --region "$REGION" 2>/dev/null)
|
|
|
|
|
CURRENT_ACCOUNT=$(echo "$CALLER_IDENTITY" | grep -o '"Account": "[^"]*"' | cut -d'"' -f4)
|
|
|
|
|
echo "✅ AWS credentials configured"
|
|
|
|
|
echo " Current Account: $CURRENT_ACCOUNT"
|
|
|
|
|
echo " Target Account: $ACCOUNT_ID"
|
|
|
|
|
|
|
|
|
|
if [ "$CURRENT_ACCOUNT" != "$ACCOUNT_ID" ]; then
|
|
|
|
|
echo "⚠️ Warning: Current account ($CURRENT_ACCOUNT) differs from config account ($ACCOUNT_ID)"
|
|
|
|
|
echo " Proceeding with current account credentials..."
|
|
|
|
|
fi
|
|
|
|
|
else
|
fix (02-use-cases): AWS Operations Agent updated with AgentCore Runtime (#177)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
---------
Co-authored-by: name <alias@amazon.com>
2025-07-31 11:59:30 -07:00
|
|
|
|
echo "❌ AWS credentials not configured or invalid"
|
Configuration Management Fixes (#223)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
* feat: Enhance AWS Operations Agent with improved testing and deployment
- Update README with new local container testing approach using run-*-local-container.sh scripts
- Replace deprecated SAM-based MCP Lambda deployment with ZIP-based deployment
- Add no-cache flag to Docker builds to ensure clean builds
- Update deployment scripts to use consolidated configuration files
- Add comprehensive cleanup scripts for all deployment components
- Improve error handling and credential validation in deployment scripts
- Add new MCP tool deployment using ZIP packaging instead of Docker containers
- Update configuration management to use dynamic-config.yaml structure
- Add local testing capabilities with containerized agents
- Remove outdated test scripts and replace with interactive chat client approach
* fix: Update IAM policy configurations
- Update bac-permissions-policy.json with enhanced permissions
- Update bac-trust-policy.json for improved trust relationships
* fix: Update Docker configurations for agent runtimes
- Update Dockerfile.diy with improved container configuration
- Update Dockerfile.sdk with enhanced build settings
* fix: Update OAuth iframe flow configuration
- Update iframe-oauth-flow.html with improved OAuth handling
* feat: Update AWS Operations Agent configuration and cleanup
- Update IAM permissions policy with enhanced access controls
- Update IAM trust policy with improved security conditions
- Enhance OAuth iframe flow with better UX and error handling
- Improve chatbot client with enhanced local testing capabilities
- Remove cache files and duplicate code for cleaner repository
* docs: Add architecture diagrams and update README
- Add architecture-2.jpg and flow.jpg diagrams for better visualization
- Update README.md with enhanced documentation and diagrams
* Save current work before resolving merge conflicts
* Keep AWS-operations-agent changes (local version takes precedence)
* Fix: Remove merge conflict markers from AWS-operations-agent files - restore clean version
* Fix deployment and cleanup script issues
Major improvements and fixes:
Configuration Management:
- Fix role assignment in gateway creation (use bac-execution-role instead of Lambda role)
- Add missing role_arn cleanup in MCP tool deletion script
- Fix OAuth provider deletion script configuration clearing
- Improve memory deletion script to preserve quote consistency
- Add Lambda invoke permissions to bac-permissions-policy.json
Script Improvements:
- Reorganize deletion scripts: 11-delete-oauth-provider.sh, 12-delete-memory.sh, 13-cleanup-everything.sh
- Fix interactive prompt handling in cleanup scripts (echo -e format)
- Add yq support with sed fallbacks for better YAML manipulation
- Remove obsolete 04-deploy-mcp-tool-lambda-zip.sh script
Architecture Fixes:
- Correct gateway role assignment to use runtime.role_arn (bac-execution-role)
- Ensure proper role separation between gateway and Lambda execution
- Fix configuration cleanup to clear all dynamic config fields consistently
Documentation:
- Update README with clear configuration instructions
- Maintain security best practices with placeholder values
- Add comprehensive deployment and cleanup guidance
These changes address systematic issues with cleanup scripts, role assignments,
and configuration management while maintaining security best practices.
* Update README.md with comprehensive documentation
Enhanced documentation includes:
- Complete project structure with 75 files
- Step-by-step deployment guide with all 13 scripts
- Clear configuration instructions with security best practices
- Dual agent architecture documentation (DIY + SDK)
- Authentication flow and security implementation details
- Troubleshooting guide and operational procedures
- Local testing and container development guidance
- Tool integration and MCP protocol documentation
The README now provides complete guidance for deploying and operating
the AWS Support Agent with Amazon Bedrock AgentCore system.
---------
Co-authored-by: name <alias@amazon.com>
2025-08-09 13:51:24 -07:00
|
|
|
|
echo " Please run: aws configure or aws sso login --profile <your-profile>"
|
|
|
|
|
echo " Current AWS config:"
|
|
|
|
|
aws configure list
|
fix (02-use-cases): AWS Operations Agent updated with AgentCore Runtime (#177)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
---------
Co-authored-by: name <alias@amazon.com>
2025-07-31 11:59:30 -07:00
|
|
|
|
exit 1
|
|
|
|
|
fi
|
|
|
|
|
echo ""
|
|
|
|
|
|
|
|
|
|
# Function to delete runtime
|
|
|
|
|
delete_runtime() {
|
|
|
|
|
local runtime_arn="$1"
|
|
|
|
|
local runtime_name="$2"
|
|
|
|
|
|
|
|
|
|
if [ -z "$runtime_arn" ]; then
|
|
|
|
|
echo " ⚠️ No $runtime_name runtime ARN found - skipping"
|
|
|
|
|
return 0
|
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
# Extract runtime ID from ARN (format: arn:aws:bedrock-agentcore:region:account:runtime/runtime-id)
|
|
|
|
|
local runtime_id=$(echo "$runtime_arn" | sed 's|.*runtime/||')
|
|
|
|
|
|
|
|
|
|
echo "🗑️ Deleting $runtime_name runtime..."
|
|
|
|
|
echo " ARN: $runtime_arn"
|
|
|
|
|
echo " ID: $runtime_id"
|
|
|
|
|
|
|
|
|
|
# Check if runtime exists first
|
|
|
|
|
if ! aws bedrock-agentcore-control get-agent-runtime \
|
|
|
|
|
--agent-runtime-id "$runtime_id" \
|
|
|
|
|
--region "$REGION" >/dev/null 2>&1; then
|
|
|
|
|
echo " ℹ️ $runtime_name runtime not found or already deleted"
|
|
|
|
|
return 0
|
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
# Delete the runtime
|
|
|
|
|
if aws bedrock-agentcore-control delete-agent-runtime \
|
|
|
|
|
--agent-runtime-id "$runtime_id" \
|
|
|
|
|
--region "$REGION" 2>/dev/null; then
|
|
|
|
|
echo " ✅ $runtime_name runtime deletion initiated"
|
|
|
|
|
|
|
|
|
|
# Wait for deletion to complete
|
|
|
|
|
echo " ⏳ Waiting for $runtime_name runtime deletion to complete..."
|
|
|
|
|
local max_attempts=30
|
|
|
|
|
local attempt=1
|
|
|
|
|
|
|
|
|
|
while [ $attempt -le $max_attempts ]; do
|
|
|
|
|
if ! aws bedrock-agentcore-control get-agent-runtime \
|
|
|
|
|
--agent-runtime-id "$runtime_id" \
|
|
|
|
|
--region "$REGION" >/dev/null 2>&1; then
|
|
|
|
|
echo " ✅ $runtime_name runtime deleted successfully"
|
|
|
|
|
return 0
|
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
echo " ⏳ Attempt $attempt/$max_attempts - $runtime_name runtime still exists..."
|
|
|
|
|
sleep 10
|
|
|
|
|
((attempt++))
|
|
|
|
|
done
|
|
|
|
|
|
|
|
|
|
echo " ⚠️ $runtime_name runtime deletion timeout - may still be in progress"
|
|
|
|
|
return 1
|
|
|
|
|
else
|
|
|
|
|
echo " ❌ Failed to delete $runtime_name runtime"
|
|
|
|
|
echo " 💡 This might be normal if the runtime was already deleted"
|
|
|
|
|
return 1
|
|
|
|
|
fi
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# Get runtime ARNs from dynamic configuration
|
|
|
|
|
echo "📖 Reading runtime ARNs from dynamic configuration..."
|
Configuration Management Fixes (#223)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
* feat: Enhance AWS Operations Agent with improved testing and deployment
- Update README with new local container testing approach using run-*-local-container.sh scripts
- Replace deprecated SAM-based MCP Lambda deployment with ZIP-based deployment
- Add no-cache flag to Docker builds to ensure clean builds
- Update deployment scripts to use consolidated configuration files
- Add comprehensive cleanup scripts for all deployment components
- Improve error handling and credential validation in deployment scripts
- Add new MCP tool deployment using ZIP packaging instead of Docker containers
- Update configuration management to use dynamic-config.yaml structure
- Add local testing capabilities with containerized agents
- Remove outdated test scripts and replace with interactive chat client approach
* fix: Update IAM policy configurations
- Update bac-permissions-policy.json with enhanced permissions
- Update bac-trust-policy.json for improved trust relationships
* fix: Update Docker configurations for agent runtimes
- Update Dockerfile.diy with improved container configuration
- Update Dockerfile.sdk with enhanced build settings
* fix: Update OAuth iframe flow configuration
- Update iframe-oauth-flow.html with improved OAuth handling
* feat: Update AWS Operations Agent configuration and cleanup
- Update IAM permissions policy with enhanced access controls
- Update IAM trust policy with improved security conditions
- Enhance OAuth iframe flow with better UX and error handling
- Improve chatbot client with enhanced local testing capabilities
- Remove cache files and duplicate code for cleaner repository
* docs: Add architecture diagrams and update README
- Add architecture-2.jpg and flow.jpg diagrams for better visualization
- Update README.md with enhanced documentation and diagrams
* Save current work before resolving merge conflicts
* Keep AWS-operations-agent changes (local version takes precedence)
* Fix: Remove merge conflict markers from AWS-operations-agent files - restore clean version
* Fix deployment and cleanup script issues
Major improvements and fixes:
Configuration Management:
- Fix role assignment in gateway creation (use bac-execution-role instead of Lambda role)
- Add missing role_arn cleanup in MCP tool deletion script
- Fix OAuth provider deletion script configuration clearing
- Improve memory deletion script to preserve quote consistency
- Add Lambda invoke permissions to bac-permissions-policy.json
Script Improvements:
- Reorganize deletion scripts: 11-delete-oauth-provider.sh, 12-delete-memory.sh, 13-cleanup-everything.sh
- Fix interactive prompt handling in cleanup scripts (echo -e format)
- Add yq support with sed fallbacks for better YAML manipulation
- Remove obsolete 04-deploy-mcp-tool-lambda-zip.sh script
Architecture Fixes:
- Correct gateway role assignment to use runtime.role_arn (bac-execution-role)
- Ensure proper role separation between gateway and Lambda execution
- Fix configuration cleanup to clear all dynamic config fields consistently
Documentation:
- Update README with clear configuration instructions
- Maintain security best practices with placeholder values
- Add comprehensive deployment and cleanup guidance
These changes address systematic issues with cleanup scripts, role assignments,
and configuration management while maintaining security best practices.
* Update README.md with comprehensive documentation
Enhanced documentation includes:
- Complete project structure with 75 files
- Step-by-step deployment guide with all 13 scripts
- Clear configuration instructions with security best practices
- Dual agent architecture documentation (DIY + SDK)
- Authentication flow and security implementation details
- Troubleshooting guide and operational procedures
- Local testing and container development guidance
- Tool integration and MCP protocol documentation
The README now provides complete guidance for deploying and operating
the AWS Support Agent with Amazon Bedrock AgentCore system.
---------
Co-authored-by: name <alias@amazon.com>
2025-08-09 13:51:24 -07:00
|
|
|
|
DYNAMIC_CONFIG="${CONFIG_DIR}/dynamic-config.yaml"
|
fix (02-use-cases): AWS Operations Agent updated with AgentCore Runtime (#177)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
---------
Co-authored-by: name <alias@amazon.com>
2025-07-31 11:59:30 -07:00
|
|
|
|
|
|
|
|
|
if [ -f "$DYNAMIC_CONFIG" ]; then
|
|
|
|
|
if command -v yq >/dev/null 2>&1; then
|
|
|
|
|
DIY_RUNTIME_ARN=$(yq eval '.runtime.diy_agent.arn' "$DYNAMIC_CONFIG")
|
|
|
|
|
SDK_RUNTIME_ARN=$(yq eval '.runtime.sdk_agent.arn' "$DYNAMIC_CONFIG")
|
|
|
|
|
else
|
|
|
|
|
# Fallback parsing
|
|
|
|
|
DIY_RUNTIME_ARN=$(grep -A 10 "diy_agent:" "$DYNAMIC_CONFIG" | grep "arn:" | head -1 | sed 's/.*arn: *["'\'']*\([^"'\'']*\)["'\'']*$/\1/')
|
|
|
|
|
SDK_RUNTIME_ARN=$(grep -A 10 "sdk_agent:" "$DYNAMIC_CONFIG" | grep "arn:" | head -1 | sed 's/.*arn: *["'\'']*\([^"'\'']*\)["'\'']*$/\1/')
|
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
# Clean up empty values
|
|
|
|
|
[ "$DIY_RUNTIME_ARN" = "null" ] && DIY_RUNTIME_ARN=""
|
|
|
|
|
[ "$SDK_RUNTIME_ARN" = "null" ] && SDK_RUNTIME_ARN=""
|
|
|
|
|
|
|
|
|
|
echo " DIY Runtime ARN: ${DIY_RUNTIME_ARN:-'Not configured'}"
|
|
|
|
|
echo " SDK Runtime ARN: ${SDK_RUNTIME_ARN:-'Not configured'}"
|
|
|
|
|
else
|
|
|
|
|
echo " ⚠️ Dynamic configuration file not found: $DYNAMIC_CONFIG"
|
|
|
|
|
DIY_RUNTIME_ARN=""
|
|
|
|
|
SDK_RUNTIME_ARN=""
|
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
echo ""
|
|
|
|
|
|
|
|
|
|
# List all existing runtimes for reference
|
|
|
|
|
echo "📋 Listing all existing runtimes in account..."
|
|
|
|
|
if aws bedrock-agentcore-control list-agent-runtimes --region "$REGION" >/dev/null 2>&1; then
|
|
|
|
|
runtime_list=$(aws bedrock-agentcore-control list-agent-runtimes --region "$REGION" --query 'agentRuntimes[*].{Name:agentRuntimeName,ID:agentRuntimeId,Status:status}' --output table 2>/dev/null)
|
|
|
|
|
if [ -n "$runtime_list" ] && echo "$runtime_list" | grep -q "agentcoreDIYTest\|bac_runtime"; then
|
|
|
|
|
echo "$runtime_list"
|
|
|
|
|
else
|
|
|
|
|
echo " ℹ️ No runtimes found in account"
|
|
|
|
|
fi
|
|
|
|
|
else
|
|
|
|
|
echo " ⚠️ Unable to list runtimes (may be a permissions issue)"
|
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
echo ""
|
|
|
|
|
|
|
|
|
|
# Delete runtimes
|
|
|
|
|
echo "🗑️ Starting runtime deletion process..."
|
|
|
|
|
echo ""
|
|
|
|
|
|
|
|
|
|
# Delete DIY runtime
|
|
|
|
|
if [ -n "$DIY_RUNTIME_ARN" ]; then
|
|
|
|
|
delete_runtime "$DIY_RUNTIME_ARN" "DIY"
|
|
|
|
|
else
|
|
|
|
|
echo "⚠️ No DIY runtime found to delete"
|
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
echo ""
|
|
|
|
|
|
|
|
|
|
# Delete SDK runtime
|
|
|
|
|
if [ -n "$SDK_RUNTIME_ARN" ]; then
|
|
|
|
|
delete_runtime "$SDK_RUNTIME_ARN" "SDK"
|
|
|
|
|
else
|
|
|
|
|
echo "⚠️ No SDK runtime found to delete"
|
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
echo ""
|
|
|
|
|
|
|
|
|
|
# Update dynamic configuration to clear runtime ARNs
|
|
|
|
|
echo "📝 Updating dynamic configuration to clear runtime ARNs..."
|
|
|
|
|
if command -v yq >/dev/null 2>&1; then
|
|
|
|
|
yq eval '.runtime.diy_agent.arn = ""' -i "$DYNAMIC_CONFIG"
|
Configuration Management Fixes (#223)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
* feat: Enhance AWS Operations Agent with improved testing and deployment
- Update README with new local container testing approach using run-*-local-container.sh scripts
- Replace deprecated SAM-based MCP Lambda deployment with ZIP-based deployment
- Add no-cache flag to Docker builds to ensure clean builds
- Update deployment scripts to use consolidated configuration files
- Add comprehensive cleanup scripts for all deployment components
- Improve error handling and credential validation in deployment scripts
- Add new MCP tool deployment using ZIP packaging instead of Docker containers
- Update configuration management to use dynamic-config.yaml structure
- Add local testing capabilities with containerized agents
- Remove outdated test scripts and replace with interactive chat client approach
* fix: Update IAM policy configurations
- Update bac-permissions-policy.json with enhanced permissions
- Update bac-trust-policy.json for improved trust relationships
* fix: Update Docker configurations for agent runtimes
- Update Dockerfile.diy with improved container configuration
- Update Dockerfile.sdk with enhanced build settings
* fix: Update OAuth iframe flow configuration
- Update iframe-oauth-flow.html with improved OAuth handling
* feat: Update AWS Operations Agent configuration and cleanup
- Update IAM permissions policy with enhanced access controls
- Update IAM trust policy with improved security conditions
- Enhance OAuth iframe flow with better UX and error handling
- Improve chatbot client with enhanced local testing capabilities
- Remove cache files and duplicate code for cleaner repository
* docs: Add architecture diagrams and update README
- Add architecture-2.jpg and flow.jpg diagrams for better visualization
- Update README.md with enhanced documentation and diagrams
* Save current work before resolving merge conflicts
* Keep AWS-operations-agent changes (local version takes precedence)
* Fix: Remove merge conflict markers from AWS-operations-agent files - restore clean version
* Fix deployment and cleanup script issues
Major improvements and fixes:
Configuration Management:
- Fix role assignment in gateway creation (use bac-execution-role instead of Lambda role)
- Add missing role_arn cleanup in MCP tool deletion script
- Fix OAuth provider deletion script configuration clearing
- Improve memory deletion script to preserve quote consistency
- Add Lambda invoke permissions to bac-permissions-policy.json
Script Improvements:
- Reorganize deletion scripts: 11-delete-oauth-provider.sh, 12-delete-memory.sh, 13-cleanup-everything.sh
- Fix interactive prompt handling in cleanup scripts (echo -e format)
- Add yq support with sed fallbacks for better YAML manipulation
- Remove obsolete 04-deploy-mcp-tool-lambda-zip.sh script
Architecture Fixes:
- Correct gateway role assignment to use runtime.role_arn (bac-execution-role)
- Ensure proper role separation between gateway and Lambda execution
- Fix configuration cleanup to clear all dynamic config fields consistently
Documentation:
- Update README with clear configuration instructions
- Maintain security best practices with placeholder values
- Add comprehensive deployment and cleanup guidance
These changes address systematic issues with cleanup scripts, role assignments,
and configuration management while maintaining security best practices.
* Update README.md with comprehensive documentation
Enhanced documentation includes:
- Complete project structure with 75 files
- Step-by-step deployment guide with all 13 scripts
- Clear configuration instructions with security best practices
- Dual agent architecture documentation (DIY + SDK)
- Authentication flow and security implementation details
- Troubleshooting guide and operational procedures
- Local testing and container development guidance
- Tool integration and MCP protocol documentation
The README now provides complete guidance for deploying and operating
the AWS Support Agent with Amazon Bedrock AgentCore system.
---------
Co-authored-by: name <alias@amazon.com>
2025-08-09 13:51:24 -07:00
|
|
|
|
yq eval '.runtime.diy_agent.ecr_uri = ""' -i "$DYNAMIC_CONFIG"
|
fix (02-use-cases): AWS Operations Agent updated with AgentCore Runtime (#177)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
---------
Co-authored-by: name <alias@amazon.com>
2025-07-31 11:59:30 -07:00
|
|
|
|
yq eval '.runtime.diy_agent.endpoint_arn = ""' -i "$DYNAMIC_CONFIG"
|
|
|
|
|
yq eval '.runtime.sdk_agent.arn = ""' -i "$DYNAMIC_CONFIG"
|
Configuration Management Fixes (#223)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
* feat: Enhance AWS Operations Agent with improved testing and deployment
- Update README with new local container testing approach using run-*-local-container.sh scripts
- Replace deprecated SAM-based MCP Lambda deployment with ZIP-based deployment
- Add no-cache flag to Docker builds to ensure clean builds
- Update deployment scripts to use consolidated configuration files
- Add comprehensive cleanup scripts for all deployment components
- Improve error handling and credential validation in deployment scripts
- Add new MCP tool deployment using ZIP packaging instead of Docker containers
- Update configuration management to use dynamic-config.yaml structure
- Add local testing capabilities with containerized agents
- Remove outdated test scripts and replace with interactive chat client approach
* fix: Update IAM policy configurations
- Update bac-permissions-policy.json with enhanced permissions
- Update bac-trust-policy.json for improved trust relationships
* fix: Update Docker configurations for agent runtimes
- Update Dockerfile.diy with improved container configuration
- Update Dockerfile.sdk with enhanced build settings
* fix: Update OAuth iframe flow configuration
- Update iframe-oauth-flow.html with improved OAuth handling
* feat: Update AWS Operations Agent configuration and cleanup
- Update IAM permissions policy with enhanced access controls
- Update IAM trust policy with improved security conditions
- Enhance OAuth iframe flow with better UX and error handling
- Improve chatbot client with enhanced local testing capabilities
- Remove cache files and duplicate code for cleaner repository
* docs: Add architecture diagrams and update README
- Add architecture-2.jpg and flow.jpg diagrams for better visualization
- Update README.md with enhanced documentation and diagrams
* Save current work before resolving merge conflicts
* Keep AWS-operations-agent changes (local version takes precedence)
* Fix: Remove merge conflict markers from AWS-operations-agent files - restore clean version
* Fix deployment and cleanup script issues
Major improvements and fixes:
Configuration Management:
- Fix role assignment in gateway creation (use bac-execution-role instead of Lambda role)
- Add missing role_arn cleanup in MCP tool deletion script
- Fix OAuth provider deletion script configuration clearing
- Improve memory deletion script to preserve quote consistency
- Add Lambda invoke permissions to bac-permissions-policy.json
Script Improvements:
- Reorganize deletion scripts: 11-delete-oauth-provider.sh, 12-delete-memory.sh, 13-cleanup-everything.sh
- Fix interactive prompt handling in cleanup scripts (echo -e format)
- Add yq support with sed fallbacks for better YAML manipulation
- Remove obsolete 04-deploy-mcp-tool-lambda-zip.sh script
Architecture Fixes:
- Correct gateway role assignment to use runtime.role_arn (bac-execution-role)
- Ensure proper role separation between gateway and Lambda execution
- Fix configuration cleanup to clear all dynamic config fields consistently
Documentation:
- Update README with clear configuration instructions
- Maintain security best practices with placeholder values
- Add comprehensive deployment and cleanup guidance
These changes address systematic issues with cleanup scripts, role assignments,
and configuration management while maintaining security best practices.
* Update README.md with comprehensive documentation
Enhanced documentation includes:
- Complete project structure with 75 files
- Step-by-step deployment guide with all 13 scripts
- Clear configuration instructions with security best practices
- Dual agent architecture documentation (DIY + SDK)
- Authentication flow and security implementation details
- Troubleshooting guide and operational procedures
- Local testing and container development guidance
- Tool integration and MCP protocol documentation
The README now provides complete guidance for deploying and operating
the AWS Support Agent with Amazon Bedrock AgentCore system.
---------
Co-authored-by: name <alias@amazon.com>
2025-08-09 13:51:24 -07:00
|
|
|
|
yq eval '.runtime.sdk_agent.ecr_uri = ""' -i "$DYNAMIC_CONFIG"
|
fix (02-use-cases): AWS Operations Agent updated with AgentCore Runtime (#177)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
---------
Co-authored-by: name <alias@amazon.com>
2025-07-31 11:59:30 -07:00
|
|
|
|
yq eval '.runtime.sdk_agent.endpoint_arn = ""' -i "$DYNAMIC_CONFIG"
|
Configuration Management Fixes (#223)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
* feat: Enhance AWS Operations Agent with improved testing and deployment
- Update README with new local container testing approach using run-*-local-container.sh scripts
- Replace deprecated SAM-based MCP Lambda deployment with ZIP-based deployment
- Add no-cache flag to Docker builds to ensure clean builds
- Update deployment scripts to use consolidated configuration files
- Add comprehensive cleanup scripts for all deployment components
- Improve error handling and credential validation in deployment scripts
- Add new MCP tool deployment using ZIP packaging instead of Docker containers
- Update configuration management to use dynamic-config.yaml structure
- Add local testing capabilities with containerized agents
- Remove outdated test scripts and replace with interactive chat client approach
* fix: Update IAM policy configurations
- Update bac-permissions-policy.json with enhanced permissions
- Update bac-trust-policy.json for improved trust relationships
* fix: Update Docker configurations for agent runtimes
- Update Dockerfile.diy with improved container configuration
- Update Dockerfile.sdk with enhanced build settings
* fix: Update OAuth iframe flow configuration
- Update iframe-oauth-flow.html with improved OAuth handling
* feat: Update AWS Operations Agent configuration and cleanup
- Update IAM permissions policy with enhanced access controls
- Update IAM trust policy with improved security conditions
- Enhance OAuth iframe flow with better UX and error handling
- Improve chatbot client with enhanced local testing capabilities
- Remove cache files and duplicate code for cleaner repository
* docs: Add architecture diagrams and update README
- Add architecture-2.jpg and flow.jpg diagrams for better visualization
- Update README.md with enhanced documentation and diagrams
* Save current work before resolving merge conflicts
* Keep AWS-operations-agent changes (local version takes precedence)
* Fix: Remove merge conflict markers from AWS-operations-agent files - restore clean version
* Fix deployment and cleanup script issues
Major improvements and fixes:
Configuration Management:
- Fix role assignment in gateway creation (use bac-execution-role instead of Lambda role)
- Add missing role_arn cleanup in MCP tool deletion script
- Fix OAuth provider deletion script configuration clearing
- Improve memory deletion script to preserve quote consistency
- Add Lambda invoke permissions to bac-permissions-policy.json
Script Improvements:
- Reorganize deletion scripts: 11-delete-oauth-provider.sh, 12-delete-memory.sh, 13-cleanup-everything.sh
- Fix interactive prompt handling in cleanup scripts (echo -e format)
- Add yq support with sed fallbacks for better YAML manipulation
- Remove obsolete 04-deploy-mcp-tool-lambda-zip.sh script
Architecture Fixes:
- Correct gateway role assignment to use runtime.role_arn (bac-execution-role)
- Ensure proper role separation between gateway and Lambda execution
- Fix configuration cleanup to clear all dynamic config fields consistently
Documentation:
- Update README with clear configuration instructions
- Maintain security best practices with placeholder values
- Add comprehensive deployment and cleanup guidance
These changes address systematic issues with cleanup scripts, role assignments,
and configuration management while maintaining security best practices.
* Update README.md with comprehensive documentation
Enhanced documentation includes:
- Complete project structure with 75 files
- Step-by-step deployment guide with all 13 scripts
- Clear configuration instructions with security best practices
- Dual agent architecture documentation (DIY + SDK)
- Authentication flow and security implementation details
- Troubleshooting guide and operational procedures
- Local testing and container development guidance
- Tool integration and MCP protocol documentation
The README now provides complete guidance for deploying and operating
the AWS Support Agent with Amazon Bedrock AgentCore system.
---------
Co-authored-by: name <alias@amazon.com>
2025-08-09 13:51:24 -07:00
|
|
|
|
echo " ✅ Dynamic configuration updated - runtime ARNs and ECR URIs cleared"
|
fix (02-use-cases): AWS Operations Agent updated with AgentCore Runtime (#177)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
---------
Co-authored-by: name <alias@amazon.com>
2025-07-31 11:59:30 -07:00
|
|
|
|
else
|
Configuration Management Fixes (#223)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
* feat: Enhance AWS Operations Agent with improved testing and deployment
- Update README with new local container testing approach using run-*-local-container.sh scripts
- Replace deprecated SAM-based MCP Lambda deployment with ZIP-based deployment
- Add no-cache flag to Docker builds to ensure clean builds
- Update deployment scripts to use consolidated configuration files
- Add comprehensive cleanup scripts for all deployment components
- Improve error handling and credential validation in deployment scripts
- Add new MCP tool deployment using ZIP packaging instead of Docker containers
- Update configuration management to use dynamic-config.yaml structure
- Add local testing capabilities with containerized agents
- Remove outdated test scripts and replace with interactive chat client approach
* fix: Update IAM policy configurations
- Update bac-permissions-policy.json with enhanced permissions
- Update bac-trust-policy.json for improved trust relationships
* fix: Update Docker configurations for agent runtimes
- Update Dockerfile.diy with improved container configuration
- Update Dockerfile.sdk with enhanced build settings
* fix: Update OAuth iframe flow configuration
- Update iframe-oauth-flow.html with improved OAuth handling
* feat: Update AWS Operations Agent configuration and cleanup
- Update IAM permissions policy with enhanced access controls
- Update IAM trust policy with improved security conditions
- Enhance OAuth iframe flow with better UX and error handling
- Improve chatbot client with enhanced local testing capabilities
- Remove cache files and duplicate code for cleaner repository
* docs: Add architecture diagrams and update README
- Add architecture-2.jpg and flow.jpg diagrams for better visualization
- Update README.md with enhanced documentation and diagrams
* Save current work before resolving merge conflicts
* Keep AWS-operations-agent changes (local version takes precedence)
* Fix: Remove merge conflict markers from AWS-operations-agent files - restore clean version
* Fix deployment and cleanup script issues
Major improvements and fixes:
Configuration Management:
- Fix role assignment in gateway creation (use bac-execution-role instead of Lambda role)
- Add missing role_arn cleanup in MCP tool deletion script
- Fix OAuth provider deletion script configuration clearing
- Improve memory deletion script to preserve quote consistency
- Add Lambda invoke permissions to bac-permissions-policy.json
Script Improvements:
- Reorganize deletion scripts: 11-delete-oauth-provider.sh, 12-delete-memory.sh, 13-cleanup-everything.sh
- Fix interactive prompt handling in cleanup scripts (echo -e format)
- Add yq support with sed fallbacks for better YAML manipulation
- Remove obsolete 04-deploy-mcp-tool-lambda-zip.sh script
Architecture Fixes:
- Correct gateway role assignment to use runtime.role_arn (bac-execution-role)
- Ensure proper role separation between gateway and Lambda execution
- Fix configuration cleanup to clear all dynamic config fields consistently
Documentation:
- Update README with clear configuration instructions
- Maintain security best practices with placeholder values
- Add comprehensive deployment and cleanup guidance
These changes address systematic issues with cleanup scripts, role assignments,
and configuration management while maintaining security best practices.
* Update README.md with comprehensive documentation
Enhanced documentation includes:
- Complete project structure with 75 files
- Step-by-step deployment guide with all 13 scripts
- Clear configuration instructions with security best practices
- Dual agent architecture documentation (DIY + SDK)
- Authentication flow and security implementation details
- Troubleshooting guide and operational procedures
- Local testing and container development guidance
- Tool integration and MCP protocol documentation
The README now provides complete guidance for deploying and operating
the AWS Support Agent with Amazon Bedrock AgentCore system.
---------
Co-authored-by: name <alias@amazon.com>
2025-08-09 13:51:24 -07:00
|
|
|
|
echo " ⚠️ yq not found - using sed fallback to clear runtime fields"
|
|
|
|
|
# Fallback: use sed to clear the fields
|
|
|
|
|
sed -i '' \
|
|
|
|
|
-e 's|arn: "arn:aws:bedrock-agentcore:.*"|arn: ""|g' \
|
|
|
|
|
-e 's|ecr_uri: ".*\.dkr\.ecr\..*"|ecr_uri: ""|g' \
|
|
|
|
|
-e 's|endpoint_arn: "arn:aws:bedrock-agentcore:.*"|endpoint_arn: ""|g' \
|
|
|
|
|
"$DYNAMIC_CONFIG"
|
|
|
|
|
echo " ✅ Dynamic configuration updated - runtime ARNs and ECR URIs cleared"
|
fix (02-use-cases): AWS Operations Agent updated with AgentCore Runtime (#177)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
---------
Co-authored-by: name <alias@amazon.com>
2025-07-31 11:59:30 -07:00
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
echo ""
|
|
|
|
|
|
|
|
|
|
# Optional: Clean up ECR repositories
|
|
|
|
|
echo "🧹 Optional: Clean up ECR repositories..."
|
|
|
|
|
echo " This will delete Docker images but keep the repositories"
|
|
|
|
|
|
|
|
|
|
ECR_REPOS=("bac-runtime-repo-diy" "bac-runtime-repo-sdk")
|
|
|
|
|
|
|
|
|
|
for repo in "${ECR_REPOS[@]}"; do
|
|
|
|
|
echo " Checking ECR repository: $repo"
|
|
|
|
|
|
|
|
|
|
# List images in repository
|
|
|
|
|
if aws ecr describe-images --repository-name "$repo" --region "$REGION" >/dev/null 2>&1; then
|
|
|
|
|
echo " 📦 Found ECR repository: $repo"
|
|
|
|
|
|
|
|
|
|
# Get image digests
|
|
|
|
|
image_digests=$(aws ecr list-images --repository-name "$repo" --region "$REGION" --query 'imageIds[*].imageDigest' --output text 2>/dev/null)
|
|
|
|
|
|
|
|
|
|
if [ -n "$image_digests" ] && [ "$image_digests" != "None" ]; then
|
|
|
|
|
echo " 🗑️ Deleting images from $repo..."
|
|
|
|
|
for digest in $image_digests; do
|
|
|
|
|
aws ecr batch-delete-image \
|
|
|
|
|
--repository-name "$repo" \
|
|
|
|
|
--image-ids imageDigest="$digest" \
|
|
|
|
|
--region "$REGION" >/dev/null 2>&1
|
|
|
|
|
done
|
|
|
|
|
echo " ✅ Images deleted from $repo"
|
|
|
|
|
else
|
|
|
|
|
echo " ℹ️ No images found in $repo"
|
|
|
|
|
fi
|
|
|
|
|
else
|
|
|
|
|
echo " ℹ️ ECR repository $repo not found or not accessible"
|
|
|
|
|
fi
|
|
|
|
|
done
|
|
|
|
|
|
|
|
|
|
echo ""
|
|
|
|
|
echo "✅ Runtime cleanup completed!"
|
|
|
|
|
echo ""
|
|
|
|
|
echo "📋 Summary:"
|
|
|
|
|
echo " • Deleted all AgentCore runtimes"
|
|
|
|
|
echo " • Cleared runtime ARNs from dynamic configuration"
|
|
|
|
|
echo " • Cleaned up ECR repository images"
|
|
|
|
|
echo ""
|
|
|
|
|
echo "💡 Next steps:"
|
Configuration Management Fixes (#223)
* feat: Add AWS Operations Agent with AgentCore Runtime
- Complete rewrite of AWS Operations Agent using Amazon Bedrock AgentCore
- Added comprehensive deployment scripts for DIY and SDK runtime modes
- Implemented OAuth2/PKCE authentication with Okta integration
- Added MCP (Model Context Protocol) tool support for AWS service operations
- Sanitized all sensitive information (account IDs, domains, client IDs) with placeholders
- Added support for 17 AWS services: EC2, S3, Lambda, CloudFormation, IAM, RDS, CloudWatch, Cost Explorer, ECS, EKS, SNS, SQS, DynamoDB, Route53, API Gateway, SES, Bedrock, SageMaker
- Includes chatbot client, gateway management scripts, and comprehensive testing
- Ready for public GitHub with security-cleared configuration files
Security: All sensitive values replaced with <YOUR_AWS_ACCOUNT_ID>, <YOUR_OKTA_DOMAIN>, <YOUR_OKTA_CLIENT_ID> placeholders
* Update AWS Operations Agent architecture diagram
* feat: Enhance AWS Operations Agent with improved testing and deployment
- Update README with new local container testing approach using run-*-local-container.sh scripts
- Replace deprecated SAM-based MCP Lambda deployment with ZIP-based deployment
- Add no-cache flag to Docker builds to ensure clean builds
- Update deployment scripts to use consolidated configuration files
- Add comprehensive cleanup scripts for all deployment components
- Improve error handling and credential validation in deployment scripts
- Add new MCP tool deployment using ZIP packaging instead of Docker containers
- Update configuration management to use dynamic-config.yaml structure
- Add local testing capabilities with containerized agents
- Remove outdated test scripts and replace with interactive chat client approach
* fix: Update IAM policy configurations
- Update bac-permissions-policy.json with enhanced permissions
- Update bac-trust-policy.json for improved trust relationships
* fix: Update Docker configurations for agent runtimes
- Update Dockerfile.diy with improved container configuration
- Update Dockerfile.sdk with enhanced build settings
* fix: Update OAuth iframe flow configuration
- Update iframe-oauth-flow.html with improved OAuth handling
* feat: Update AWS Operations Agent configuration and cleanup
- Update IAM permissions policy with enhanced access controls
- Update IAM trust policy with improved security conditions
- Enhance OAuth iframe flow with better UX and error handling
- Improve chatbot client with enhanced local testing capabilities
- Remove cache files and duplicate code for cleaner repository
* docs: Add architecture diagrams and update README
- Add architecture-2.jpg and flow.jpg diagrams for better visualization
- Update README.md with enhanced documentation and diagrams
* Save current work before resolving merge conflicts
* Keep AWS-operations-agent changes (local version takes precedence)
* Fix: Remove merge conflict markers from AWS-operations-agent files - restore clean version
* Fix deployment and cleanup script issues
Major improvements and fixes:
Configuration Management:
- Fix role assignment in gateway creation (use bac-execution-role instead of Lambda role)
- Add missing role_arn cleanup in MCP tool deletion script
- Fix OAuth provider deletion script configuration clearing
- Improve memory deletion script to preserve quote consistency
- Add Lambda invoke permissions to bac-permissions-policy.json
Script Improvements:
- Reorganize deletion scripts: 11-delete-oauth-provider.sh, 12-delete-memory.sh, 13-cleanup-everything.sh
- Fix interactive prompt handling in cleanup scripts (echo -e format)
- Add yq support with sed fallbacks for better YAML manipulation
- Remove obsolete 04-deploy-mcp-tool-lambda-zip.sh script
Architecture Fixes:
- Correct gateway role assignment to use runtime.role_arn (bac-execution-role)
- Ensure proper role separation between gateway and Lambda execution
- Fix configuration cleanup to clear all dynamic config fields consistently
Documentation:
- Update README with clear configuration instructions
- Maintain security best practices with placeholder values
- Add comprehensive deployment and cleanup guidance
These changes address systematic issues with cleanup scripts, role assignments,
and configuration management while maintaining security best practices.
* Update README.md with comprehensive documentation
Enhanced documentation includes:
- Complete project structure with 75 files
- Step-by-step deployment guide with all 13 scripts
- Clear configuration instructions with security best practices
- Dual agent architecture documentation (DIY + SDK)
- Authentication flow and security implementation details
- Troubleshooting guide and operational procedures
- Local testing and container development guidance
- Tool integration and MCP protocol documentation
The README now provides complete guidance for deploying and operating
the AWS Support Agent with Amazon Bedrock AgentCore system.
---------
Co-authored-by: name <alias@amazon.com>
2025-08-09 13:51:24 -07:00
|
|
|
|
echo " • Run 09-delete-all-gateways-targets.sh to delete gateways and targets"
|
|
|
|
|
echo " • Run 10-delete-mcp-tool-deployment.sh to delete MCP Lambda"
|
|
|
|
|
echo " • Run 11-delete-oauth-provider.sh for complete cleanup"
|
|
|
|
|
echo " • Run 12-delete-memory.sh to delete memory"
|